python从音频文件中提取音频频谱

您可以使用scipy计算并可视化频谱和频谱图，对于此测试，我使用了以下音频文件：vignesh.wav

from scipy.io import wavfile # scipy library to read wav filesimport numpy as npAudioname = "vignesh.wav" # Audio Filefs, Audiodata = wavfile.read(AudioName)# Plot the audio signal in timeimport matplotlib.pyplot as pltplt.plot(Audiodata)plt.title('Audio signal in time',size=16)# spectrumfrom scipy.fftpack import fft # fourier transformn = len(Audiodata) AudioFreq = fft(Audiodata)AudioFreq = AudioFreq[0:int(np.ceil((n+1)/2.0))] #Half of the spectrumMagFreq = np.abs(AudioFreq) # MagnitudeMagFreq = MagFreq / float(n)# power spectrumMagFreq = MagFreq**2if n % 2 > 0: # ffte odd     MagFreq[1:len(MagFreq)] = MagFreq[1:len(MagFreq)] * 2else:# fft even    MagFreq[1:len(MagFreq) -1] = MagFreq[1:len(MagFreq) - 1] * 2plt.figure()freqAxis = np.arange(0,int(np.ceil((n+1)/2.0)), 1.0) * (fs / n);plt.plot(freqAxis/1000.0, 10*np.log10(MagFreq)) #Power spectrumplt.xlabel('Frequency (kHz)'); plt.ylabel('Power spectrum (dB)');#Spectrogramfrom scipy import signalN = 512 #Number of point in the fftf, t, Sxx = signal.spectrogram(Audiodata, fs,window = signal.blackman(N),nfft=N)plt.figure()plt.pcolormesh(t, f,10*np.log10(Sxx)) # dB spectrogram#plt.pcolormesh(t, f,Sxx) # Lineal spectrogramplt.ylabel('Frequency [Hz]')plt.xlabel('Time [seg]')plt.title('Spectrogram with scipy.signal',size=16);plt.show()

我测试了所有代码，它可以工作，您需要numpy，matplotlib和scipy。

干杯